MATDENSE: add MatDenseReplaceArray() and MatDenseCUDAReplaceArray()Add few interface checks
MATDENSE: add API to access columns as vectors
MATMPIDENSE: support CUDAMatSeqDense: add support to check for symmetricityAdd array accessors routinesfix MatSetRandom for leading dimensionUse PetscSF for MatMult- uses the right communica
MATMPIDENSE: support CUDAMatSeqDense: add support to check for symmetricityAdd array accessors routinesfix MatSetRandom for leading dimensionUse PetscSF for MatMult- uses the right communication pattern instead of point-to-point- can take advantage of CUDA aware MPIFix bugs related with LDAFix direct usage of cpu memory: use MatDenseGetArray (and variants) insteadFix MatZeroRowsFix MatView in Binary for SeqDense
show more ...
Merge remote-tracking branch 'origin/jolivet/fix-symlink-free' into maint
Minor fixes and improvements* Typos* MatMatSolve() improvements* MatDense[Get|Restore]ColumnF90()* MatKAIJGetScaledIdentity()
Single petscdir.mk
Revert "enable MatSetOption() for matproduct; Reported by Nourgaliev, Robert Nr <nourgaliev1@llnl.gov>"This reverts commit 0e1ed72ee065c9f36858e956742a5e16988d3676.
MatMatMultSymbolic with DENSE output: use MatSetUp instead of SetPreallocationThis way we can preserve the local array if already present
enable MatSetOption() for matproduct; Reported by Nourgaliev, Robert Nr <nourgaliev1@llnl.gov>add MatSetType() in MatProductSetFromOptions_Atype_Btype_Ctype()fix MatSetOption_MPIAIJ for case MAT_US
enable MatSetOption() for matproduct; Reported by Nourgaliev, Robert Nr <nourgaliev1@llnl.gov>add MatSetType() in MatProductSetFromOptions_Atype_Btype_Ctype()fix MatSetOption_MPIAIJ for case MAT_USE_INODES
Add the product type and matrix types for the error report in MatProductSetFromOptions_matA_matB_matC()Requested by Jed Brown
Typos
build: add more support for not needing to set PETSC_DIR yet build with PETSc, also support for GNU make to directly use "make test" instead of "make -f gmakefile.test"Still needs -include ../petsc
build: add more support for not needing to set PETSC_DIR yet build with PETSc, also support for GNU make to directly use "make test" instead of "make -f gmakefile.test"Still needs -include ../petscdir.mk in many of the makefilesStill needs the link for ../petscdir.mk in many directoriesGNUMakefile: call legacy makefile recursively instead of including itGNUMakefile: promote default "all" target; "libs" builds libpetsc*GNUMakefile: If gnumake < 4.2 prefer makefile wrapper interface over direct gmakefile interface to avoid the following warningsgmakefile.test:92: arch-ci-linux-cxx-cmplx-pkgs-64idx/tests/testfiles: No such file or directorygmakefile:67: arch-ci-linux-cxx-cmplx-pkgs-64idx/lib/petsc/conf/files: No such file or directoryCommit-type: testing-fix, feature, usabilityThanks-to: Jed Brown jed@jedbrown.org
This branch reorganizes the API of mat-mat operations: A*B, At*B, A*Bt, PtAP, RARt, A*B*C- See matproduct.c for detailed description of new API- removed API function XXXSymbolic() and XXXNumeric()
This branch reorganizes the API of mat-mat operations: A*B, At*B, A*Bt, PtAP, RARt, A*B*C- See matproduct.c for detailed description of new API- removed API function XXXSymbolic() and XXXNumeric()- removed subroutines MatMatMult_xxx, MatPtAP_xxx, ...- modified MatxxxSymbolic_XXX() prototype (product is an input now)- selection of algorithm is in MatProductSetFromOptions_xxx()
MATDENSE: Add support for MPI-IO binary viewers
PetscBinaryWrite: Remove `istemp` boolean flag
Remove usage of PETSC_HAVE_FORTRAN_STDCALL, PETSC_BLASLAPACK_STDCALL, HAVE_FORTRAN_MIXED_STR_ARG flags - as Compaq f90 compiler is no longer supported
Merge remote-tracking branch 'origin/maint'
Bug fix: computing MG complexity had integer overflow. Would only occur for very large problemsAlso fixed code that computes parallel matrix storage information to communicate with PetscLogDouble i
Bug fix: computing MG complexity had integer overflow. Would only occur for very large problemsAlso fixed code that computes parallel matrix storage information to communicate with PetscLogDouble instead of PetscReal.Commit-type: bug-fixReported-by: Mark Lohry <mlohry@gmail.com>
Support for MatMatMult with Nest and MPIDense
Merged in jczhang/mat-remove-unnecessary-global-IS (pull request #1816)Remove unnecessary global IS when setting up MvctxApproved-by: BarryFSmith <bsmith@mcs.anl.gov>Approved-by: Jed Brown <jed@
Merged in jczhang/mat-remove-unnecessary-global-IS (pull request #1816)Remove unnecessary global IS when setting up MvctxApproved-by: BarryFSmith <bsmith@mcs.anl.gov>Approved-by: Jed Brown <jed@59a2.org>
Merged in barry/optimize-aij-da (pull request #1762)Non-numeric optimizations focused on AIJ, MatFDColoring, and DMCreateMatrix_DA_*AIJ, looking to improve performance in GPU environments
Non-numeric optimizations focused on AIJ, MatFDColoring, and DMCreateMatrix_DA_*AIJ, looking to improve performance in GPU environments1) PetscCalloc*() now uses system calloc()2) Merged some Pets
Non-numeric optimizations focused on AIJ, MatFDColoring, and DMCreateMatrix_DA_*AIJ, looking to improve performance in GPU environments1) PetscCalloc*() now uses system calloc()2) Merged some PetscMalloc*()3) Eliminated unneeded PetscCalloc*()4) Removed some memory allocations and copies in MatFDColoringSetUp(), added local variables for better compiler optimization5) Added MatSetValues_SeqAIJ_SortedFull(), added MatSetOption(MAT_SORTED_FULL)6) Optimized DMCreateMatrix_DA_*AIJ for nonperiodic case to automatically have sorted columns (faster MatSetValues() times)7) Eliminated call to PetscMemzero() in PetscFree()Commit-type: style-fix, feature
Remove unnecessary global IS when setting up MvctxISCreateGeneral(((PetscObject)mat)->comm..) will incur MPI_Allreduce on the communicator.
Merged in haplav/feature-matload-dense-hdf5 (pull request #1795)MatLoad_Dense_HDF5Approved-by: BarryFSmith <bsmith@mcs.anl.gov>
format code similar to VecLoad_Default()Requested-by: "Smith, Barry F." <bsmith@mcs.anl.gov>
12345678910>>...34